SketchQL Demonstration: Zero-shot Video Moment Querying with Sketches
Summary: SketchQL: a VDBMS that lets users compose complex event queries by sketching object trajectories (drag-and-drop). Uses a pre-trained trajectory-similarity encoder to perform zero-shot similarity search over videos; demo showcases GUI and end-to-end retrieval. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Renzhi Wu (Georgia Institute of Technology)
- 2. Pramod Chunduri (Georgia Institute of Technology)
- 3. Dristi J Shah (Georgia Institute of Technology)
- 4. Ashmitha Julius Aravind (Georgia Institute of Technology)
- 5. Ali Payani (Cisco)
- 6. Xu Chu (Georgia Institute of Technology)
- 7. Joy Arulraj (Georgia Institute of Technology)
- 8. Kexin Rong (Georgia Institute of Technology)
BibTeX Citation
@article{wu_vldb24,
title = {{SketchQL Demonstration: Zero-shot Video Moment Querying with Sketches}},
author = {Wu, Renzhi and Chunduri, Pramod and Shah, Dristi J and Aravind, Ashmitha Julius and Payani, Ali and Chu, Xu and Arulraj, Joy and Rong, Kexin},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {12},
pages = {4429--4432},
doi = {10.14778/3685800.3685892},
url = {https://doi.org/10.14778/3685800.3685892},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,670 | MAST: Towards Efficient Analytical Query Processing on Point Cloud Data | 2025 | SIGMOD | 5.093636e-05 |
| 10,795 | Scalable Complex Event Processing on Video Streams | 2025 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 569 | BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics | 2020 | VLDB | 0.00016348191 |
| 1,042 | MIRIS: Fast Object Track Queries in Video | 2020 | SIGMOD | 0.00012451966 |
| 2,933 | EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views | 2022 | SIGMOD | 7.9474026e-05 |
| 3,365 | Spatial and Temporal Constrained Ranked Retrieval over Videos | 2022 | VLDB | 7.4763252e-05 |
| 9,408 | SketchQL: Video Moment Querying with a Visual Query Interface | 2024 | SIGMOD | 5.2750967e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,743 | VQLens: A Demonstration of Vector Query Execution Analysis | 2025 | SIGMOD |
| 2 | 3,968 | Qetch: Time Series Querying with Expressive Sketches | 2018 | SIGMOD |
| 3 | 5,966 | VOCAL: Video Organization and Interactive Compositional AnaLytics | 2022 | CIDR |
| 4 | 3,410 | SVQ: Streaming Video Queries | 2019 | SIGMOD |
| 5 | 8,362 | EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions | 2023 | VLDB |
| 6 | 9,925 | DoveDB: A Declarative and Low-Latency Video Database | 2023 | VLDB |
| 7 | 6,912 | SENSOR: Data-driven Construction of Sketch-based Visual Query Interfaces for Time Series Data | 2022 | VLDB |
| 8 | 11,483 | EQUI-VOCAL Demonstration: Synthesizing Video Queries from User Interactions | 2023 | VLDB |
| 9 | 11,268 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB |
| 10 | 9,408 | SketchQL: Video Moment Querying with a Visual Query Interface | 2024 | SIGMOD |